add tokenizer

Browse files

Files changed (3) hide show

special_tokens_map.json +1 -1
tokenizer.json +0 -0
tokenizer_config.json +1 -1

special_tokens_map.json CHANGED Viewed

	@@ -1 +1 @@
1	- {~~"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"~~}


1	+ {}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json CHANGED Viewed

@@ -1 +1 @@

- {"do_lower_case": true, "do_basic_tokenize": true, "never_split": null, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "tokenizer_file": "/Users/hamzakazmi/.cache/huggingface/transformers/534479488c54aeaf9c3406f647aa2ec13648c06771ffe269edabebd4c412da1d.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4", "name_or_path": "bert-base-uncased", "tokenizer_class": "~~BertTokenizer~~"}


1	+ {"do_lower_case": true, "special_tokens_map_file": null, "name_or_path": "bert-base-uncased", "tokenizer_class": "PreTrainedTokenizerFast"}